Related Experiment Video
Updated: May 17, 2026
Lumped-Parameter and Finite Element Modeling of Heart Failure with Preserved Ejection Fraction
Published on: February 13, 2021
Concordance of Large Language Model Recommendations with Multidisciplinary Heart Team Decisions in Coronary
Armaun D Rouhi1, Shreyas V Menon2, Yazid K Ghanem3
1Washington University in St. Louis School of Medicine, St. Louis, MO, USA.
Insights
Large language models (LLMs) show potential as decision support tools for multidisciplinary heart teams (HTs), achieving 73% pooled agreement. However, LLM accuracy can be limited by outdated data and lack of transparency, requiring further prospective evaluation.
Area of Science:
- Cardiology
- Artificial Intelligence
- Medical Decision Support
Background:
- The multidisciplinary heart team (HT) is crucial for complex cardiovascular disease decisions.
- Large language models (LLMs) are emerging as potential clinical decision support tools.
- Evidence on LLM concordance with HT decisions is limited.
Purpose of the Study:
- To synthesize evidence on LLM recommendations versus HT decisions.
- To quantitatively estimate the agreement between LLMs and HTs.
- To identify factors influencing LLM-HT concordance.
Main Methods:
- A systematic literature search was conducted across PubMed, Scopus, and Web of Science.
- Included studies evaluated LLM recommendations against multidisciplinary HT decisions (Nov 2022 - Feb 2026).
- Random-effects meta-analysis was used to pool agreement proportions.
Main Results:
- Four retrospective studies on coronary revascularization and aortic valve intervention were analyzed.
- LLM-HT concordance ranged from 65-82% for coronary revascularization and 77% for aortic valve intervention.
- Pooled agreement was 0.73 (95% CI 0.60-0.83), with substantial heterogeneity; discordance arose from outdated data and lack of transparency.
Conclusions:
- LLMs show preliminary potential as adjunctive decision support for HTs.
- Misclassifications can occur with complex patient factors and conflicting guidelines.
- Further prospective studies across diverse LLMs are needed before clinical recommendation.
Introduction:
The multidisciplinary heart team (HT) remains the cornerstone of decision-making for complex cardiovascular disease. Large language models (LLMs) and other generative artificial intelligence models have recently emerged as potential decision support tools across diverse clinical settings. We sought to synthesize current evidence and quantitatively estimate concordance between LLM recommendations and HT decisions.
Methods:
A literature search was performed using PubMed, Scopus, and Web of Science for primary studies published between November 2022 and February 2026 that evaluated recommendations by LLMs against multidisciplinary HT decisions. Studies reporting overall agreement were included for quantitative pooling. Random-effects meta-analysis was performed to determine proportion of agreement.
Results:
Four retrospective concordance studies were included regarding decision-making in coronary revascularization and aortic valve intervention. LLM-HT concordance ranged from 65% to 82% for coronary revascularization and was 77% for aortic valve intervention. In random-effects meta-analysis, the pooled agreement between LLM recommendations and HT decisions was 0.73 (95% CI 0.60-0.83) with substantial heterogeneity. Discordance stemmed from LLM reliance on outdated trial evidence and limited transparency regarding utilized data, with misclassifications observed in cases of octogenarians with aortic stenosis. Detailed prompts generally improved accuracy and reliability of LLM recommendations.
Conclusion:
These preliminary findings suggest LLMs may have potential as adjunctive decision support tools for multidisciplinary HTs. There remains potential for misclassification when patient-specific factors and conflicting guidelines complicate decision-making. Further prospective evaluation across diverse LLMs is essential before clinical deployment can be recommended.
Related Concept Videos
01:25Aortic Regurgitation III: Medical Management
01:21Rheumatic Heart Disease III: Medical Management
01:26Mitral Stenosis III: Medical Management
01:27Coronary Artery Disease V: Interprofessional Care
01:25Mitral Regurgitation III: Medical Management
01:30Acute Coronary Syndrome III: Diagnostic Studies